Author:

Keywords:

Range image, Thermal image, Image fusion, Person Detection, Upsampling

Abstract:

Detecting and tracking people in images is an attractive method to monitor their movements. It is based on passive, non-contact sensors and hence does not disturb or distract the subjects. The analysis of the extracted position and pose data can be used in applications such as security and safety monitoring, home automation, patient monitoring or behavior analysis. However, detecting people in images is a challenging problem. Differences in pose, clothing and lighting (along with other factors) cause a lot of variation in their appearance. Some solutions have been proposed but they typically have mediocre accuracy, suffer from severe limitations, require large amounts of annotated training data and are computationally expensive. To overcome these issues, we propose a system based on fused range and thermal infrared images. These measurements show considerably less variation and provide more meaningful information. We provide a brief introduction to the sensor technology used and propose a calibration method. Several data fusion algorithms are compared and their performance is assessed on a simulated data set. The results of initial experiments are shown and the measurement errors and the challenges they present are discussed. The resulting fused data are used to efficiently detect people in a fixed camera setup. The system can be extended to include person tracking.